Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1]  884  419  462  119  540   30  807  315  103  467  360  797  670  335  492 1000  709  363  717  951
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1]  540  119  709  103   NA  363  492  462   NA  951  884  717   30  797  360  807  335  315  419   NA  467 1000  670
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 4 1 4 5 1 5 4 4 1 2
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "o" "l" "k" "h" "c" "W" "A" "R" "L" "Y"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 16 20
which( manyNumbersWithNA > 900 )
[1] 10 22
which( is.na( manyNumbersWithNA ) )
[1]  5  9 20

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 1000  951
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 1000  951
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 1000  951

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "W" "A" "R" "L" "Y"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "o" "l" "k" "h" "c"
manyNumbers %in% 300:600
 [1] FALSE  TRUE  TRUE FALSE  TRUE FALSE FALSE  TRUE FALSE  TRUE  TRUE FALSE FALSE  TRUE  TRUE FALSE FALSE  TRUE FALSE FALSE
which( manyNumbers %in% 300:600 )
[1]  2  3  5  8 10 11 14 15 18
sum( manyNumbers %in% 300:600 )
[1] 9

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" "small" "large" "small" NA      "small" "small" "small" NA      "large" "large" "large" "small" "large" "small" "large" "small" "small" "small" NA     
[21] "small" "large" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "small"   "large"   "small"   "UNKNOWN" "small"   "small"   "small"   "UNKNOWN" "large"   "large"   "large"   "small"   "large"   "small"   "large"  
[17] "small"   "small"   "small"   "UNKNOWN" "small"   "large"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]  540    0  709    0   NA    0    0    0   NA  951  884  717    0  797    0  807    0    0    0   NA    0 1000  670

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 4 1 5 2
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  4  1  5  2
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE FALSE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 22
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 1000
which.min( manyNumbersWithNA )
[1] 13
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 30
range( manyNumbersWithNA, na.rm = TRUE )
[1]   30 1000

Sorting/ordering of vectors

manyNumbersWithNA
 [1]  540  119  709  103   NA  363  492  462   NA  951  884  717   30  797  360  807  335  315  419   NA  467 1000  670
sort( manyNumbersWithNA )
 [1]   30  103  119  315  335  360  363  419  462  467  492  540  670  709  717  797  807  884  951 1000
sort( manyNumbersWithNA, na.last = TRUE )
 [1]   30  103  119  315  335  360  363  419  462  467  492  540  670  709  717  797  807  884  951 1000   NA   NA   NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 1000  951  884  807  797  717  709  670  540  492  467  462  419  363  360  335  315  119  103   30   NA   NA   NA
manyNumbersWithNA[1:5]
[1] 540 119 709 103  NA
order( manyNumbersWithNA[1:5] )
[1] 4 2 1 3 5
rank( manyNumbersWithNA[1:5] )
[1] 3 2 4 1 5
sort( mixedLetters )
 [1] "A" "c" "h" "k" "l" "L" "o" "R" "W" "Y"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 1.0 2.5 7.0 6.0 9.0 2.5 9.0 9.0 4.5 4.5
rank( manyDuplicates, ties.method = "min" )
 [1] 1 2 7 6 8 2 8 8 4 4
rank( manyDuplicates, ties.method = "random" )
 [1]  1  3  7  6  9  2 10  8  4  5

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.000000000 -0.500000000  0.000000000  0.500000000  1.000000000  0.984953958  0.555261570 -0.379901989  0.279385372  0.224925650  0.003661972 -0.123236368
[13]  0.225783036 -0.116126674 -0.270554952
round( v, 0 )
 [1] -1  0  0  0  1  1  1  0  0  0  0  0  0  0  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  1.0  0.6 -0.4  0.3  0.2  0.0 -0.1  0.2 -0.1 -0.3
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.98  0.56 -0.38  0.28  0.22  0.00 -0.12  0.23 -0.12 -0.27
floor( v )
 [1] -1 -1  0  0  1  0  0 -1  0  0  0 -1  0 -1 -1
ceiling( v )
 [1] -1  0  0  1  1  1  1  0  1  1  1  0  1  0  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2024 Biomedical Data Sciences (BDS) | LUMC